test_runner: replace black with ruff format (#6268)

## Problem

`black` is slow sometimes, we can replace it with `ruff format` (a new
feature in 0.1.2 [0]), which produces pretty similar to black style [1].

On my local machine (MacBook M1 Pro 16GB):
```
# `black` on main
$ hyperfine "BLACK_CACHE_DIR=/dev/null poetry run black ."
Benchmark 1: BLACK_CACHE_DIR=/dev/null poetry run black .
  Time (mean ± σ):      3.131 s ±  0.090 s    [User: 5.194 s, System: 0.859 s]
  Range (min … max):    3.047 s …  3.354 s    10 runs
```
```
# `ruff format` on the current PR
$ hyperfine "RUFF_NO_CACHE=true poetry run ruff format"      
Benchmark 1: RUFF_NO_CACHE=true poetry run ruff format
  Time (mean ± σ):     300.7 ms ±  50.2 ms    [User: 259.5 ms, System: 76.1 ms]
  Range (min … max):   267.5 ms … 420.2 ms    10 runs
```

## Summary of changes
- Replace `black` with `ruff format` everywhere

- [0] https://docs.astral.sh/ruff/formatter/
- [1] https://docs.astral.sh/ruff/formatter/#black-compatibility

.github/workflows/build_and_test.yml

@@ -105,11 +105,11 @@ jobs:
       - name: Install Python deps
         run: ./scripts/pysync
 
-      - name: Run ruff to ensure code format
-        run: poetry run ruff .
+      - name: Run `ruff check` to ensure code format
+        run: poetry run ruff check .
 
-      - name: Run black to ensure code format
-        run: poetry run black --diff --check .
+      - name: Run `ruff format` to ensure code format
+        run: poetry run ruff format --check .
 
       - name: Run mypy to check types
         run: poetry run mypy .

docs/sourcetree.md

@@ -129,13 +129,13 @@ Run `poetry shell` to activate the virtual environment.
 Alternatively, use `poetry run` to run a single command in the venv, e.g. `poetry run pytest`.
 
 ### Obligatory checks
-We force code formatting via `black`, `ruff`, and type hints via `mypy`.
+We force code formatting via `ruff`, and type hints via `mypy`.
 Run the following commands in the repository's root (next to `pyproject.toml`):
 
 ```bash
-poetry run black .  # All code is reformatted
-poetry run ruff .  # Python linter
-poetry run mypy .  # Ensure there are no typing errors
+poetry run ruff format . # All code is reformatted
+poetry run ruff check .  # Python linter
+poetry run mypy .        # Ensure there are no typing errors
 ```
 
 **WARNING**: do not run `mypy` from a directory other than the root of the repository.

pre-commit.py

@@ -36,17 +36,17 @@ def rustfmt(fix_inplace: bool = False, no_color: bool = False) -> str:
     return cmd
 
 
-def black(fix_inplace: bool) -> str:
-    cmd = "poetry run black"
-    if not fix_inplace:
-        cmd += " --diff --check"
+def ruff_check(fix_inplace: bool) -> str:
+    cmd = "poetry run ruff check"
+    if fix_inplace:
+        cmd += " --fix"
     return cmd
 
 
-def ruff(fix_inplace: bool) -> str:
-    cmd = "poetry run ruff"
-    if fix_inplace:
-        cmd += " --fix"
+def ruff_format(fix_inplace: bool) -> str:
+    cmd = "poetry run ruff format"
+    if not fix_inplace:
+        cmd += " --diff --check"
     return cmd
 
 
@@ -109,16 +109,16 @@ def check(name: str, suffix: str, cmd: str, changed_files: List[str], no_color:
         no_color=args.no_color,
     )
     check(
-        name="black",
+        name="ruff check",
         suffix=".py",
-        cmd=black(fix_inplace=args.fix_inplace),
+        cmd=ruff_check(fix_inplace=args.fix_inplace),
         changed_files=files,
         no_color=args.no_color,
     )
     check(
-        name="ruff",
+        name="ruff format",
         suffix=".py",
-        cmd=ruff(fix_inplace=args.fix_inplace),
+        cmd=ruff_format(fix_inplace=args.fix_inplace),
         changed_files=files,
         no_color=args.no_color,
     )

pyproject.toml

@@ -40,22 +40,13 @@ pytest-split = "^0.8.1"
 zstandard = "^0.21.0"
 
 [tool.poetry.group.dev.dependencies]
-black = "^23.3.0"
 mypy = "==1.3.0"
-ruff = "^0.0.269"
+ruff = "^0.1.11"
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]
 build-backend = "poetry.core.masonry.api"
 
-[tool.black]
-line-length = 100
-extend-exclude = '''
-/(
-    vendor
-)/
-'''
-
 [tool.mypy]
 exclude = "^vendor/"
 check_untyped_defs = true
@@ -82,11 +73,14 @@ ignore_missing_imports = true
 [tool.ruff]
 target-version = "py39"
 extend-exclude = ["vendor/"]
-ignore = ["E501"]
+ignore = [
+    "E501", # Line too long, we don't want to be too strict about it
+]
 select = [
     "E", # pycodestyle
     "F", # Pyflakes
     "I", # isort
     "W", # pycodestyle
     "B", # bugbear
 ]
+line-length = 100 # this setting is rather guidance, it won't fail if it can't make the shorter

scripts/export_import_between_pageservers.py

@@ -63,7 +63,7 @@ def subprocess_capture(capture_dir: str, cmd: List[str], **kwargs: Any) -> str:
     If those files already exist, we will overwrite them.
     Returns basepath for files with captured output.
     """
-    assert type(cmd) is list
+    assert isinstance(cmd, list)
     base = os.path.basename(cmd[0]) + "_{}".format(global_counter())
     basepath = os.path.join(capture_dir, base)
     stdout_filename = basepath + ".stdout"

scripts/reformat

@@ -6,5 +6,5 @@ set -euox pipefail
 echo 'Reformatting Rust code'
 cargo fmt
 echo 'Reformatting Python code'
-poetry run ruff --fix test_runner scripts
-poetry run black test_runner scripts
+poetry run ruff check --fix test_runner scripts
+poetry run ruff format test_runner scripts

test_runner/fixtures/neon_fixtures.py

@@ -1101,8 +1101,8 @@ def raw_cli(
         If `local_binpath` is true, then we are invoking a test utility
         """
 
-        assert type(arguments) == list
-        assert type(self.COMMAND) == str
+        assert isinstance(arguments, list)
+        assert isinstance(self.COMMAND, str)
 
         if local_binpath:
             # Test utility

test_runner/fixtures/pageserver/http.py

@@ -365,9 +365,9 @@ def tenant_size_and_modelinputs(self, tenant_id: TenantId) -> Tuple[int, Dict[st
         assert isinstance(res, dict)
         assert TenantId(res["id"]) == tenant_id
         size = res["size"]
-        assert type(size) == int
+        assert isinstance(size, int)
         inputs = res["inputs"]
-        assert type(inputs) is dict
+        assert isinstance(inputs, dict)
         return (size, inputs)
 
     def tenant_size_debug(self, tenant_id: TenantId) -> str: